You bring the Wildlife Brain to life on real hardware — deploying, optimising, and running Flox’s AI on the Edge device so it detects and responds to wildlife reliably, in the field, in real time.
About the role
You own the AI runtime on Flox Edge: taking models from the training team and making them run fast, reliably, and within the hardware’s constraints out in the field.
What you’ll do
- Deploy and optimise AI models for real-time inference on Edge hardware
- Build the on-device pipeline from sensor input to detection to response
- Profile and tune for latency, power, and memory constraints
- Implement monitoring for model drift and field performance
- Collaborate with the AI, acoustic, and hardware teams on the full loop
What you bring
- Strong experience deploying ML models to embedded or edge devices
- Fluency in Python and C/C++; familiarity with inference runtimes and optimisation
- Understanding of the realities of running AI outside the data center
- Pragmatic, field-first engineering mindset
- Fluent in English
Location & flexibility
Based in Stockholm with hybrid flexibility. Field interactions when required.